{ "slug": "smart-signal-blind-spots", "title": "Over 56% of failed drives had no count on four strong SMART signals", "kind": "dataset", "summary": "Over 56% of failed drives in the Google fleet studied by Pinheiro, Weber, and Barroso (FAST '07; more than 100,000 consumer PATA and SATA drives; SMART counts from December 2005 through August 2006) had no count on scan errors, reallocation count, offline reallocation, or probational count. Adding every other SMART parameter except temperature still left over 36% of failed drives at zero on all of those variables. That 56% figure is an upper bound on coverage for the four signals, not a false-positive-aware accuracy.", "license": "Small derived table of figures stated in Pinheiro, Weber, and Barroso, Failure Trends in a Large Disk Drive Population, FAST '07, proceedings pages 17-28, and of one restatement in heise online (16 February 2007). Not a Creative Commons license. USENIX's open-access notice says papers and proceedings are freely available to everyone once the event begins. That notice is not a CC grant, and the FAST '07 HTML does not grant one. This CSV is not Google's SMART repository or repairs database. Canonical files are the USENIX HTML paper and the proceedings PDF.", "licenseUrl": "https://www.usenix.org/conference/osdi18/preview1", "sourceUrl": "https://www.usenix.org/event/fast07/tech/full_papers/pinheiro/pinheiro_html/", "accessed": "2026-10-10", "rowCount": 12, "columns": [ { "name": "row_id", "type": "string", "description": "Stable id for the signal or coverage cut." }, { "name": "signal", "type": "string", "description": "SMART parameter, coverage cut, or the heise restatement of a coverage cut." }, { "name": "population", "type": "string", "description": "Fleet, media, and failure definition the row's figures belong to. Google rows are one production fleet. The heise row is a news restatement of that study, not a second fleet." }, { "name": "window", "type": "string", "description": "Observation window. Google SMART rows are December 2005 through August 2006 (2005-12/2006-08). The heise row states only about nine months." }, { "name": "prevalence_percent", "type": "number", "description": "Share of drives with a non-zero count, in percent. The number is the figure printed next to the bound in prevalence_bound, not a refit. Empty when the row is not a prevalence." }, { "name": "prevalence_bound", "type": "string", "description": "How prevalence_percent was stated: fewer-than, under, about, more-than, or point. Empty when prevalence is empty." }, { "name": "afr_factor_low", "type": "number", "description": "Low end of the stated AFR multiple versus drives with a zero count. A factor, not a percent and not a line rate. Empty when the paper states no AFR factor. Equal to afr_factor_high when the paper states one factor." }, { "name": "afr_factor_high", "type": "number", "description": "High end of that AFR multiple. Empty when afr_factor_low is empty." }, { "name": "fail_60d_factor", "type": "number", "description": "Multiple for failure within 60 days after the first count, versus drives with a zero count. Not an AFR. The paper reports a critical threshold when a count raises that probability by at least 10 times at confidence above 95%. Empty when no 60-day factor is stated." }, { "name": "fail_60d_bound", "type": "string", "description": "How fail_60d_factor was stated: point or over. Empty when the factor is empty." }, { "name": "no_count_share_percent", "type": "number", "description": "Percent of the denominator in no_count_denominator that had no failure signal for this cut. Empty when the row is not a coverage sentence." }, { "name": "no_count_share_bound", "type": "string", "description": "How no_count_share_percent was stated: over, about, or point. Empty when the share is empty." }, { "name": "no_count_denominator", "type": "string", "description": "Who the no-count share divides: failed-drives or all-drives. The paper uses both for a 36% figure. Empty when the share is empty." }, { "name": "signaled_group_failed_percent", "type": "number", "description": "Percent of drives that already had the count and then failed. Used for calibration retries only. Not an AFR and not a share of all failed drives. Empty otherwise." }, { "name": "signaled_group_failed_bound", "type": "string", "description": "How signaled_group_failed_percent was stated: about or point. Empty when that percent is empty." }, { "name": "fault", "type": "string", "description": "Named condition the signal is about, from a sentence in the cited source." }, { "name": "catches", "type": "string", "description": "What a non-zero count indicates in that source." }, { "name": "misses", "type": "string", "description": "The failure or ambiguity that count does not prove, from a sentence in the same source." }, { "name": "citation_id", "type": "string", "description": "Id into the citations list. Open that URL for the sentence." } ], "downloadPath": "/data/datasets/smart-signal-blind-spots.csv", "citations": [ { "id": "pinheiro-fast07", "title": "Failure Trends in a Large Disk Drive Population (Pinheiro, Weber, and Barroso, FAST '07, HTML)", "url": "https://www.usenix.org/event/fast07/tech/full_papers/pinheiro/pinheiro_html/", "accessed": "2026-10-10" }, { "id": "pinheiro-fast07-pdf", "title": "Failure Trends in a Large Disk Drive Population, FAST '07 proceedings PDF", "url": "https://www.usenix.org/legacy/events/fast07/tech/full_papers/pinheiro/pinheiro.pdf", "accessed": "2026-10-10" }, { "id": "heise-2007-02-16", "title": "Google-Studie zur Ausfallursache von Festplatten", "url": "https://www.heise.de/news/Google-Studie-zur-Ausfallursache-von-Festplatten-147178.html", "accessed": "2026-10-10" }, { "id": "usenix-open-access", "title": "USENIX Open Access Media notice", "url": "https://www.usenix.org/conference/osdi18/preview1", "accessed": "2026-10-10" } ] }